{"id":"https://openalex.org/W2120725344","doi":"https://doi.org/10.1109/tpami.2013.146","title":"Good Practice in Large-Scale Learning for Image Classification","display_name":"Good Practice in Large-Scale Learning for Image Classification","alternate_titles":[],"publication_year":2013,"publication_date":"2013-08-05","ids":{"openalex":"https://openalex.org/W2120725344","doi":"https://doi.org/10.1109/tpami.2013.146","mag":"2120725344","pmid":"https://pubmed.ncbi.nlm.nih.gov/24457507"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2013.146","doi":"https://doi.org/10.1109/tpami.2013.146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2013.146","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2120725344"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00835810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040372929","display_name":"Zeynep Akata","orcid":"https://orcid.org/0000-0002-1432-7747","observed_orcids":["https://orcid.org/0000-0002-1432-7747"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Zeynep Akata","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan and INRIA Rhone-Alpes, Montbonnot","LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)","Xerox Research Centre Europe [Meylan] (Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan and INRIA Rhone-Alpes, Montbonnot","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"Xerox Research Centre Europe [Meylan] (Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE - France)","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059987704","display_name":"Florent Perronnin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Florent Perronnin","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan","Xerox Research Centre Europe [Meylan] (Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe [Meylan] (Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE - France)","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010613767","display_name":"Za\u00efd Harchaoui","orcid":"https://orcid.org/0000-0003-1186-1343","observed_orcids":["https://orcid.org/0000-0003-1186-1343"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Zaid Harchaoui","raw_affiliation_strings":["INRIA Rhone-Alpes, Montbonnot","LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rhone-Alpes, Montbonnot","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":"https://orcid.org/0009-0005-7239-3741","observed_orcids":["https://orcid.org/0009-0005-7239-3741"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["INRIA Rhone-Alpes, Montbonnot","LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rhone-Alpes, Montbonnot","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"LEAR - Learning and recognition in vision (INRIA\u00a0Grenoble Rh\u00f4ne-Alpes \r\n655, avenue de l'Europe \r\n38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":17.3771,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99478231,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"507","last_page":"520"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.36739999055862427,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.36739999055862427,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2329999953508377,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11550000309944153,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-scale-image-classification","display_name":"large-scale image classification","score":0.9670000076293945},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.9710000157356262},{"id":"https://openalex.org/keywords/multi-class-svm","display_name":"multi-class SVM","score":0.8289999961853027},{"id":"https://openalex.org/keywords/ranking-svm","display_name":"ranking SVM","score":0.7609999775886536},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"stochastic gradient descent","score":0.9950000047683716},{"id":"https://openalex.org/keywords/class-rebalancing","display_name":"class rebalancing","score":0.75},{"id":"https://openalex.org/keywords/early-stopping","display_name":"early stopping","score":0.6949999928474426},{"id":"https://openalex.org/keywords/regularization","display_name":"regularization","score":0.8220000267028809},{"id":"https://openalex.org/keywords/imagenet","display_name":"ImageNet","score":0.6940000057220459},{"id":"https://openalex.org/keywords/training-speed","display_name":"training speed","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663759589195251},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6639294624328613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6354334354400635},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6345260739326477},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6230373978614807},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6206381916999817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030815243721008},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5378021597862244},{"id":"https://openalex.org/C77265313","wikidata":"https://www.wikidata.org/wiki/Q879844","display_name":"Rest (music)","level":2,"score":0.514910101890564},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.47223496437072754},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45481646060943604},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4475284218788147},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41568827629089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.412309467792511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14125296473503113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13124775886535645},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C164705383","wikidata":"https://www.wikidata.org/wiki/Q10379","display_name":"Cardiology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/tpami.2013.146","doi":"https://doi.org/10.1109/tpami.2013.146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2013.146","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:24457507","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24457507","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":"Journal Article"},{"id":"pmh:oai:HAL:hal-00835810v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00835810","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36 (3), pp.507-520. &#x27E8;10.1109/TPAMI.2013.146&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:escidoc.org:escidoc:2029025","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0019-87C1-2","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210088280","host_organization_name":"Max Planck Digital Library","host_organization_lineage":["https://openalex.org/I4210088280"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.mpg.de:item_2029025","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0019-87C1-2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.400.448","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.400.448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/83/58/10/PDF/TPAMI_minor_revision.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.657.1796","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.657.1796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-00835810/PDF/TPAMI_minor_revision.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00835810v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00835810","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36 (3), pp.507-520. &#x27E8;10.1109/TPAMI.2013.146&#x27E9;","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W2169610","https://openalex.org/W21006490","https://openalex.org/W175058090","https://openalex.org/W280632315","https://openalex.org/W1480538416","https://openalex.org/W1512098439","https://openalex.org/W1551774182","https://openalex.org/W1567125377","https://openalex.org/W1574862351","https://openalex.org/W1576962511","https://openalex.org/W1588401315","https://openalex.org/W1606858007","https://openalex.org/W1625255723","https://openalex.org/W1637435380","https://openalex.org/W1676820704","https://openalex.org/W1851597118","https://openalex.org/W1959000896","https://openalex.org/W1976921161","https://openalex.org/W1982032418","https://openalex.org/W1984309565","https://openalex.org/W1987063155","https://openalex.org/W1987435156","https://openalex.org/W2006493005","https://openalex.org/W2009543464","https://openalex.org/W2009593947","https://openalex.org/W2020733616","https://openalex.org/W2025862220","https://openalex.org/W2027922120","https://openalex.org/W2031489346","https://openalex.org/W2033379850","https://openalex.org/W2035720976","https://openalex.org/W2038597090","https://openalex.org/W2040672759","https://openalex.org/W2047221353","https://openalex.org/W2053229256","https://openalex.org/W2062292468","https://openalex.org/W2077071968","https://openalex.org/W2090042335","https://openalex.org/W2097018403","https://openalex.org/W2102765684","https://openalex.org/W2105842272","https://openalex.org/W2106191340","https://openalex.org/W2108598243","https://openalex.org/W2110764733","https://openalex.org/W2112530506","https://openalex.org/W2112865076","https://openalex.org/W2113651538","https://openalex.org/W2116444583","https://openalex.org/W2118585731","https://openalex.org/W2120480077","https://openalex.org/W2122528955","https://openalex.org/W2124509324","https://openalex.org/W2127176025","https://openalex.org/W2127279985","https://openalex.org/W2127781398","https://openalex.org/W2128154306","https://openalex.org/W2129921015","https://openalex.org/W2131846894","https://openalex.org/W2133864802","https://openalex.org/W2134557905","https://openalex.org/W2136064009","https://openalex.org/W2138516811","https://openalex.org/W2142623206","https://openalex.org/W2143042756","https://openalex.org/W2145607950","https://openalex.org/W2147238549","https://openalex.org/W2148239836","https://openalex.org/W2151103935","https://openalex.org/W2153635508","https://openalex.org/W2154579312","https://openalex.org/W2155144632","https://openalex.org/W2155490028","https://openalex.org/W2157065343","https://openalex.org/W2157791002","https://openalex.org/W2162915993","https://openalex.org/W2163922914","https://openalex.org/W2165966284","https://openalex.org/W2167057485","https://openalex.org/W2168231600","https://openalex.org/W2168371480","https://openalex.org/W2171749496","https://openalex.org/W2253807446","https://openalex.org/W2282078507","https://openalex.org/W2541822344","https://openalex.org/W2543453567","https://openalex.org/W2546302380","https://openalex.org/W3004533406","https://openalex.org/W3014813097","https://openalex.org/W3120421331","https://openalex.org/W3145063618","https://openalex.org/W4206733017","https://openalex.org/W4238404964","https://openalex.org/W4239072543","https://openalex.org/W4240768087","https://openalex.org/W4285719527","https://openalex.org/W4293857795","https://openalex.org/W4312960235","https://openalex.org/W6941183308"],"related_works":["https://openalex.org/W2127279985","https://openalex.org/W2536350606","https://openalex.org/W2128154306","https://openalex.org/W4200408376","https://openalex.org/W2101922717","https://openalex.org/W2325965525","https://openalex.org/W1975742283","https://openalex.org/W2108387768","https://openalex.org/W15119441","https://openalex.org/W7144357805"],"abstract_inverted_index":{"We":[0,10,110],"benchmark":[1],"several":[2],"SVM":[3],"objective":[4],"functions":[5],"for":[6,27,131],"large-scale":[7],"image":[8],"classification.":[9],"consider":[11],"one-versus-rest,":[12],"multiclass,":[13],"ranking,":[14],"and":[15,24,67,122,172],"weighted":[16],"approximate":[17],"ranking":[18],"SVMs.":[19],"A":[20],"comparison":[21],"of":[22,43,65,69,88,106,120,162,169,175],"online":[23,33,149],"batch":[25,39],"methods":[26,34,40],"optimizing":[28],"the":[29,61,81,94,99,104,107,117,132,160,163],"objectives":[30],"shows":[31,74],"that":[32,75,113],"perform":[35],"as":[36,38,103,141],"well":[37],"in":[41,51,96,127],"terms":[42],"classification":[44],"accuracy,":[45],"but":[46],"with":[47,148],"a":[48,85,128,166],"significant":[49,129],"gain":[50],"training":[52,62,89,147],"speed.":[53],"Using":[54],"stochastic":[55],"gradient":[56],"descent,":[57],"we":[58,155],"can":[59,125,138],"scale":[60],"to":[63,158,182],"millions":[64],"images":[66,174],"thousands":[68],"classes.":[70],"Our":[71],"experimental":[72],"evaluation":[73],"ranking-based":[76],"algorithms":[77,101],"do":[78],"not":[79],"outperform":[80],"one-versus-rest":[82,133],"strategy":[83,145],"when":[84,146],"large":[86,167],"number":[87],"examples":[90,124],"are":[91],"used.":[92],"Furthermore,":[93],"gap":[95],"accuracy":[97,181],"between":[98],"different":[100],"shrinks":[102],"dimension":[105],"features":[108],"increases.":[109],"also":[111],"show":[112],"learning":[114],"through":[115],"cross-validation":[116],"optimal":[118],"rebalancing":[119],"positive":[121],"negative":[123],"result":[126],"improvement":[130],"strategy.":[134],"Finally,":[135],"early":[136],"stopping":[137],"be":[139],"used":[140],"an":[142],"effective":[143],"regularization":[144],"algorithms.":[150],"Following":[151],"these":[152],"\"good":[153],"practices,\"":[154],"were":[156],"able":[157],"improve":[159],"state":[161],"art":[164],"on":[165],"subset":[168],"10K":[170],"classes":[171],"9M":[173],"ImageNet":[176],"from":[177],"16.7":[178],"percent":[179],"Top-1":[180],"19.1":[183],"percent.":[184]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2120725344","counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2016-06-24T00:00:00"}
